2021-01-12 TidyTuesday Artist Tate

Author: Crystal Lwi

artists <- read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-01-12/artists.csv") %>% as.data.frame()
artwork <- read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-01-12/artwork.csv") %>% as.data.frame()

artists <- artists %>% clean_names()
artwork <- artwork %>% clean_names()

artists %>% glimpse()

Rows: 3,532
Columns: 9
$ id             <int> 10093, 0, 2756, 1, 622, 2606, 9550, 623, 624, 625, 2411, 626, 627, 628, 629, 630, 2~
$ name           <chr> "Abakanowicz, Magdalena", "Abbey, Edwin Austin", "Abbott, Berenice", "Abbott, Lemue~
$ gender         <chr> "Female", "Male", "Female", "Male", "Male", "Male", "Female", "Male", "Male", "Male~
$ dates          <chr> "born 1930", "1852â\200“1911", "1898â\200“1991", "1760â\200“1803", "born 1935", "19~
$ year_of_birth  <int> 1930, 1852, 1898, 1760, 1935, 1964, 1967, 1940, 1947, 1938, 1728, 1868, 1927, 1917,~
$ year_of_death  <int> NA, 1911, 1991, 1803, NA, 1993, NA, NA, 2014, NA, 1792, 1947, 2005, 1984, 1966, 194~
$ place_of_birth <chr> "Polska", "Philadelphia, United States", "Springfield, United States", "Leicestersh~
$ place_of_death <chr> NA, "London, United Kingdom", "Monson, United States", "London, United Kingdom", NA~
$ url            <chr> "http://www.tate.org.uk/art/artists/magdalena-abakanowicz-10093", "http://www.tate.~

unique(artists$year_of_birth)

  [1] 1930 1852 1898 1760 1935 1964 1967 1940 1947 1938 1728 1868 1927 1917 1878 1895 1904 1912 1899 1767
 [21] 1959 1957 1926 1923 1953 1966 1888 1897 1905 1870 1973 1756 1785 1744 1892 1782 1916 1803 1933 1951
 [41] 1890 1804 1974 1836 1934 1971 1925 1682 1970 1921 1965 1630 1975 1982 1894 1928 1685 1936   NA 1861
 [61] 1883 1979 1815 1969 1914 1874 1978 1887 1900 1896 1929 1881 1817 1828 1893 1763 1886 1939 1945 1944
 [81] 1909 1961 1787 1775 1873 1913 1999 1958 1866 1931 1968 1832 1960 1727 1786 1751 1943 1740 1585 1910
[101] 1911 1788 1924 1977 1871 1950 1902 1922 1780 1907 1769 1626 1972 1747 1789 1741 1941 1955 1850 1906
[121] 1867 1889 1903 1872 1869 1738 1633 1743 1753 1952 1793 1946 1884 1880 1795 1875 1794 1863 1879 1942
[141] 1800 1811 1849 1962 1531 1865 1963 1762 2004 1956 1790 1932 1757 1864 1908 1949 1882 1851 1834 1734
[161] 1876 1802 1644 1937 1822 1833 1773 1629 1824 1919 1826 1948 1920 1750 1821 1901 1857 1805 1733 1813
[181] 1754 1831 1791 1810 1500 1600 1700 1847 1885 1772 1918 1723 1856 1829 1730 1759 1862 1784 1915 1846
[201] 1858 1835 1814 1855 1779 1812 1845 1799 1954 1796 1697 1843 1837 1713 1841 1844 1839 1770 1781 1710
[221] 1660 1774 1798 1988 1582 1807 1725 1662 1840 1680 1825 1572 1792 1776 1877 1609 1742 1726 1783 1717
[241] 1752 1768 1659 1748 1838 1715 1823 1735 1749 1819 1611 1827 1729 1711 1708 1853 1801 1848 1797 1632
[261] 1615 1746 1806 1816 1860 1891 1980 1830 1540 1745 1695 1859 1755 1818 1606 1976 1561 1631 1854 1724
[281] 1699 1642 1645 1640 1737 1778 1985 1698 1686 1764 1530 1692 1547 1758 1707 1777 1497 1718 1635 1701
[301] 1820 1996 1621 1593 1628 1765 1646 1842 1761 1679 1696 1674 1590 1618 1702 1992 1981 1739 1689 1681
[321] 1732 1716 1560 1771 1986 1551 1714 1647 1731 1667 1809 1577 1736 1721 1580 1722 1627 1766 1808 1605
[341] 1703 1594 1705 1675 1684 1599 1694 1641 1639 1656 1617 1652

artists %>% filter(!is.na(gender)) %>% 
  count(gender)

Given that most of the artists are male, let’s have a look at when they are born.

yr <- artists %>% filter(!is.na(year_of_birth), !is.na(gender)) %>% 
  group_by(gender) %>% 
  count(year_of_birth) %>% 
  ggplot(aes(x = year_of_birth, y = n, color = gender))+
  geom_line()+theme_bw(base_size = 13)+
  ylab("Number of artists born")+
  xlab("Year")+
  labs(title= "Artists born by year")+
  theme(plot.title = element_text(hjust = 0.5))

yr %>% ggplotly()

Starting from artists born in 1930-s the number of female artists increased.

art <- right_join(artists, artwork %>% rename(artwork_id = id, artwork_url = url), 
                  by = c("id" = 'artist_id'))
art %>% filter(!is.na(gender)) %>% 
  group_by(gender) %>% 
  count()

NA

Now we can clearly see that there are almost 50x more male artwork as compared to female.

names(art)

 [1] "id"                  "name"                "gender"              "dates"              
 [5] "year_of_birth"       "year_of_death"       "place_of_birth"      "place_of_death"     
 [9] "url"                 "artwork_id"          "accession_number"    "artist"             
[13] "artist_role"         "title"               "date_text"           "medium"             
[17] "credit_line"         "year"                "acquisition_year"    "dimensions"         
[21] "width"               "height"              "depth"               "units"              
[25] "inscription"         "thumbnail_copyright" "thumbnail_url"       "artwork_url"        

ggplotly(art %>% filter(!is.na(gender)) %>% 
  group_by(gender, year) %>% 
  count(gender) %>% 
  ggplot(aes(x = year, y = n, color = gender))+
  geom_line()+ theme_bw(base_size = 13)+
  ylab("Number of artwork")+
  xlab("Year")+
  labs(title= "Artworks by year")+
  theme(plot.title = element_text(hjust = 0.5)))

Artworks distribution show very high by males in the 1800-s century. Sharp decline in artworks in 1846 - 1964. Early 19th century of Europe was facing industrialisation. As a result of this, there could have been fewer artists during that period producing artworks. In response to these changes going on in society, the movement of Realism emerged. Realism sought to accurately portray the conditions and hardships of the poor in the hopes of changing society.

ggplotly(medium %>% filter(!is.na(decade_category), !is.na(gender)) %>% 
  ggplot(aes(x = decade_category, y = canvas, fill = gender))+
  geom_col(position = 'dodge')+
    ggtitle("Canvas by decades")+
  theme_bw())

ggplotly(medium %>% filter(!is.na(decade_category), !is.na(gender)) %>% 
  ggplot(aes(x = decade_category, y = paper, fill = gender))+
  geom_col(position = 'dodge')+
  ggtitle("Paper by decades")+
  theme_bw())